Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numbers related to statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to various sectors and economic conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comr
    -0.52
    bris
    -0.44
    amph
    -0.44
    ffiti
    -0.44
    evin
    -0.43
     newcomer
    -0.43
    atown
    -0.43
    edient
    -0.43
     ensued
    -0.43
     reformed
    -0.42
    POSITIVE LOGITS
     percent
    0.75
     crore
    0.74
     billion
    0.74
     million
    0.72
     trillion
    0.70
    %
    0.70
    000
    0.61
    00
    0.61
    million
    0.61
     pounds
    0.61
    Act Density 0.594%

    No Known Activations